fix(test): Remedy macOS-only test failure not triggered by CI (#2957)

**Summary**
A crude and OS-specific mechanism was used to detect when a path
represented a temp-file. Change that to be robust across operating
systems and localized configurations. The specific problem was for DOC
files but this PR fixes it for PPT too which was prone to the same
problem.

Author: scanny

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.13.7-dev3
+## 0.13.7-dev4
 
 ### Enhancements
 
@@ -9,6 +9,7 @@
 ### Fixes
 
 * **`partition_docx()` handles short table rows.** The DOCX format allows a table row to start late and/or end early, meaning cells at the beginning or end of a row can be omitted. While there are legitimate uses for this capability, using it in practice is relatively rare. However, it can happen unintentionally when adjusting cell borders with the mouse. Accommodate this case and generate accurate `.text` and `.metadata.text_as_html` for these tables.
+* **Remedy macOS test failure not triggered by CI.** Generalize temp-file detection beyond hard-coded Linux-specific prefix.
 
 ## 0.13.6
 

test_unstructured/partition/docx/test_doc.py

@@ -251,6 +251,21 @@ def test_partition_doc_suppresses_modified_date_from_file_by_default(mocker: Moc
     assert elements[0].metadata.last_modified is None
 
 
+def test_partition_doc_pulls_modified_date_from_file_when_date_from_file_object_arg_is_True(
+    mocker: MockFixture,
+):
+    modified_date_on_file = "2024-05-01T09:24:28"
+    mocker.patch(
+        "unstructured.partition.doc.get_last_modified_date_from_file",
+        return_value=modified_date_on_file,
+    )
+
+    with open(example_doc_path("fake.doc"), "rb") as f:
+        elements = partition_doc(file=f, date_from_file_object=True)
+
+    assert elements[0].metadata.last_modified == modified_date_on_file
+
+
 def test_partition_doc_from_file_explicit_get_metadata_date(
     mocker,
     filename="example-docs/fake.doc",

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.13.7-dev3"  # pragma: no cover
+__version__ = "0.13.7-dev4"  # pragma: no cover

unstructured/partition/docx.py

@@ -69,7 +69,12 @@
     is_possible_title,
     is_us_city_state_zip,
 )
-from unstructured.utils import dependency_exists, lazyproperty, requires_dependencies
+from unstructured.utils import (
+    dependency_exists,
+    is_temp_file_path,
+    lazyproperty,
+    requires_dependencies,
+)
 
 if dependency_exists("pypandoc"):
     import pypandoc
@@ -772,7 +777,7 @@ def _last_modified(self) -> Optional[str]:
 
         # -- if the file is on the filesystem, get its date from there --
         if file_path is not None:
-            return None if file_path.startswith("/tmp") else get_last_modified_date(file_path)
+            return None if is_temp_file_path(file_path) else get_last_modified_date(file_path)
 
         # -- otherwise, as long as user explicitly requested it, try getting it from the file-like
         # -- object (unlikely since BytesIO and its brethren have no such metadata).

unstructured/partition/pptx.py

@@ -47,7 +47,7 @@
     is_possible_title,
 )
 from unstructured.partition.utils.constants import PartitionStrategy
-from unstructured.utils import lazyproperty
+from unstructured.utils import is_temp_file_path, lazyproperty
 
 DETECTION_ORIGIN = "pptx"
 
@@ -442,7 +442,7 @@ def last_modified(self) -> Optional[str]:
         if self._file_path:
             return (
                 None
-                if self._file_path.startswith("/tmp")
+                if is_temp_file_path(self._file_path)
                 else get_last_modified_date(self._file_path)
             )
 

unstructured/utils.py

@@ -7,6 +7,7 @@
 import os
 import platform
 import subprocess
+import tempfile
 import threading
 from datetime import datetime
 from functools import wraps
@@ -75,6 +76,15 @@ def iter_tds(row_cell_strs: Sequence[str]) -> Iterator[str]:
     return f"<table>{''.join(iter_trs(matrix))}</table>" if matrix else ""
 
 
+def is_temp_file_path(file_path: str) -> bool:
+    """True when file_path is in the Python-defined tempdir.
+
+    The Python-defined temp directory is platform dependent (macOS != Linux != Windows)
+    and can also be determined by an environment variable (TMPDIR, TEMP, or TMP).
+    """
+    return file_path.startswith(tempfile.gettempdir())
+
+
 class lazyproperty(Generic[_T]):
     """Decorator like @property, but evaluated only on first access.